Senior Data Scientist - Healthcare AI

Summary:

The mission of The University of Texas M. D. Anderson Cancer Center is to eliminate cancer in Texas, the nation, and the world through outstanding programs that integrate patient care, research, prevention, and education. Core to the success of our mission is the ability to orchestrate multidimensional data, data analytics, and machine learning to create sustainable impact within a framework of responsible AI. We are building a dynamic team of machine learning engineers and data scientists that can help us consistently and responsibly accelerate the impact of AI across the enterprise, driving long-lasting improvements in cancer care.

We are seeking a Senior Data Scientist with strong expertise in designing, developing, validating, and deploying AI solutions using real-world healthcare data. This role will focus on scalable AI/ML systems tailored for oncology and healthcare, leveraging multimodal data sources such as EHRs, imaging, pathology, genomics, and operational data. The ideal candidate will have hands-on experience deploying AI models into production environments with rigorous validation protocols aligned to clinical and operational outcomes.

This role combines advanced data science with AI architecture responsibilities, emphasizing robust AI lifecycle management, regulatory compliance, and cross-functional collaboration. While experience in emerging AI fields such as generative AI and agentic AI is a plus, the core focus remains on delivering validated, impactful AI solutions in healthcare settings.

Core Responsibilities include:

AI Development & Validation
• Design, develop, validate, and deploy scalable machine learning models using multimodal healthcare datasets.
• Execute rigorous validation through pilot studies, silent trials, and performance monitoring against clinical and operational KPIs.
• Translate clinical complexities into practical AI-driven insights and actionable solutions.

AI Architecture & Lifecycle Management
• Architect scalable, reliable AI/ML pipelines optimized for production and continuous improvement.
• Manage AI model lifecycles including versioning, retraining, governance, and regulatory compliance (e.g., ISO/IEC standards, FDA, HIPAA).

Integration & AI Assurance
• Collaborate closely with multidisciplinary teams—clinicians, data engineers, ML engineers—to integrate AI effectively within clinical workflows.
• Implement robust assurance frameworks to objectively measure and enhance AI solution efficacy, safety, and reliability.

Governance & Compliance
• Maintain strict adherence to institutional policies, healthcare regulations, and ethical standards ensuring fairness, transparency, and accountability.
• Ensure comprehensive documentation to facilitate auditability, transparency, and compliance.

Collaboration & Communication
• Engage effectively with stakeholders to ensure seamless integration of AI solutions into healthcare systems (e.g., Epic, PACS).
• Clearly document workflows, model performance, and communicate results to technical and non-technical audiences alike.

Innovation & Thought Leadership
• Drive innovation by contributing to AI research and industry forums, positioning the institution as a leader in responsible healthcare AI.
• Explore emerging technologies (generative AI, agentic AI) pragmatically, identifying viable opportunities for integration.

Technical Expertise    

Hands-on experience and in-depth understanding of machine learning algorithms and modeling (e.g., supervised, unsupervised, semi-supervised or weakly supervised learning, generative models, transfer learning, optimization, etc.). 

Experience with human-in-the-loop systems and active learning for data curation, proven track record building and validating AI models on real-world data, skilled in constructing scalable data pipelines, model artifact management, and model performance analytics, experienced with MLOps tools and processes for data, features, code, and model management, strong proficiency in Python and either C++ or C#, with practical knowledge of TensorFlow, PyTorch, and Scikit-learn, experience with healthcare data types and standards (FHIR, HL7, DICOM), strong understanding of AI lifecycle management, governance, and compliance with healthcare regulations, authorship as first author on peer-reviewed publications or equivalent evidence demonstrating impactful application of AI/ML in healthcare or biomedical domains.

Analytical Expertise  
Proficient in translating complex, ambiguous healthcare challenges into structured, data-driven AI solutions.
In-depth knowledge of AI/ML model lifecycle management including ongoing monitoring, retraining, and risk mitigation strategies.
Proficient in decision-making, problem-solving, and executing AI/ML healthcare solutions.
Experience with AI model validation in clinical or operational settings, including designing assurance studies and evaluating impact on relevant KPIs.
Competent in identifying risks and formulating mitigation plans to prevent project delays.

Oral and Written Communication   
Collaborate with research data scientists, ML engineers, and software engineers to integrate machine learning models into existing systems.
Document processes, pipelines, workflows, and machine learning experiments.
Skilled in applying project management frameworks (e.g., Agile) to track progress and communicate risks and impacts to a variety of audiences.
Experience presenting complex technical concepts clearly to both technical and non-technical audiences through reports, meetings, and professional forums.
Manage stakeholder relations to facilitate solution adoption and address issues.

Other duties as assigned